Main
Lucas Moraes
I am a data professional who transits between data science and analytics. I am an evolutionary biologist by formation, having acted with statistical modelling applied to the field of bioinformatics. I program in R and Python and while I am not developing models, I am analysing them to assure their quality and scientific rigor.
Recent professional experience
Senior Data Analyst
PicPay
N/A
Present - 2022
- Statistical and experimental support for the User Knowledge Squad.
- Data analysis for the development of robust machine learning models.
- Data analysis for integrity check of models in production.
Independent consultant (Data Science & Analytics)
Freelancer
N/A
2022 - 2018
- Data compilation, cleaning, exploratory analysis and statistical modelling for reports and research projects.
- Experimental design and hypothesis testing for the resolution of questions with scientific, statistical and methodological rigor.
- Development of machine learning models for predictive or correlation analyses (e.g. linear and logistic regression, k-means, random forest and XGBoost).
Data Scientist
Melhor envio
N/A
2022 - 2021
- Customer segmentation using non supervised machine learning (K-prototypes).
- Supevised machine learning for customer churn prediction (Random Forest & XGBoost).
- Development of a analytical pipeline to monitor the activities of customers in real time, with the objective of increasing retention and detect churn, using personalized behavioral data.
- Conversion of arbitrary business metrics to robust indicators using statistical techniques (e.g. bootstrapping and hypothesis testing).
- Data viz e dashboards (ggplot2 & Looker). Presentations to non techincal audiences.
Education
Technical knowledge __________________
R
Python
SQL
Spark
Statistics
Machine Learning
Data Viz
Fluent english
Soft Skills
MsC, Genetics
Rio de Janeiro Federal University
N/A
2018 - 2016
- Hierarchical clustering and dendrogram analysis of dated phylogenetic trees to identify evolutionary distinct angiosperm lineages, integrating biological, geographical and molecular data.
- Dissertation: Conservation of evolutionary distinct brazilian angiosperm species: integrating extinction risk assessments, phylogenetic information and the state of the art knowledge of brazilian plants.
- Advisor: Carlos Guerra Schrago.
BsC, Genetics
Rio de Janeiro Federal University
N/A
2012 - 2007
- Phylogenetic and topological estimation of cetaceans using bayesian and maximum likelihood inferences for hierarchical clustering parametrization.
- Mithocondrial genome sequencing and in silico analysis.
- Monography: Phylogenetic Status and Timescale for the Diversification of Steno and Sotalia Dolphins
- Publication: Phylogenetic Status and Timescale for the Diversification of Steno and Sotalia Dolphins. PLOS ONE. https://doi.org/10.1371/journal.pone.0028297
- Advisor: Carlos Guerra Schrago.
About me
A few considerations
N/A
N/A
N/A
- I have been part of interdisciplinary teams with people from a wide variety of backgrounds and seniority levels. This gave me a keen sense of empathy and understanding about people in general. This is for me one of my most valuable assets.
- I believe in the principle of parsimony: the best way is the simplest possible, although the simplest may be complex.
- I love developing models, but I believe that well treated data coupled with a rigorous experimental design is way more important than modelling.
- This cv was generated in R!
Curiosities
N/A
N/A
N/A
- I have previously acted as a professional photographer.
- I am always on time.
- I practice free diving and spearfishing.
- I spent the beginning of my childhood in Wyoming.